{"id":"W4412902841","doi":"10.1037/dev0002050","title":"Investigating the validity of picture-based assessments across cultures and contexts: Evidence from young children in Kenya and the United States.","year":2025,"lang":"en","type":"article","venue":"Developmental Psychology","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Jacobs Foundation; Aga Khan Foundation","keywords":"Psychology; Developmental psychology; Test validity; Adolescent development; Psychometrics; Child development","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02170072,0.0004776662,0.0004157448,0.001236366,0.002388071,0.002068651,0.001163038,0.0008735562,0.003931923],"category_scores_gemma":[0.09583309,0.0007154169,0.000659558,0.001663545,0.002834406,0.004699104,0.002745792,0.001408018,0.000616906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001353553,"about_ca_system_score_gemma":0.001481291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04529738,"about_ca_topic_score_gemma":0.09214967,"domain_scores_codex":[0.9920189,0.004724429,0.0006867991,0.001127317,0.001033234,0.000409252],"domain_scores_gemma":[0.9509621,0.03008242,0.009579891,0.003621899,0.004675202,0.001078436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006243772,0.0005733491,0.9004407,0.000339964,0.0002095624,0.0002827142,0.07017343,0.0001510398,0.0007723519,0.001148767,0.001368834,0.02391499],"study_design_scores_gemma":[0.0001082464,0.000500555,0.9357119,0.0005688262,0.0001676581,0.0002945287,0.05704374,0.0003498646,0.0008228344,0.0009211192,0.003456985,0.00005364114],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935232,0.0003973675,0.0003217259,0.0001939751,0.0000226676,0.0001345748,0.0002821251,0.000003841993,0.00512049],"genre_scores_gemma":[0.9972491,0.0004564082,0.0008243597,0.0001917908,0.000006729565,0.0003967202,0.0003132769,0.000007244896,0.0005541714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04529738,"threshold_uncertainty_score":0.1147658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0450071139547364,"score_gpt":0.4149150188432443,"score_spread":0.3699079048885079,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}